summaryrefslogtreecommitdiffstats
path: root/kernel/include/linux/blk-mq.h
diff options
context:
space:
mode:
authorYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 12:17:53 -0700
committerYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 15:44:42 -0700
commit9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 (patch)
tree1c9cafbcd35f783a87880a10f85d1a060db1a563 /kernel/include/linux/blk-mq.h
parent98260f3884f4a202f9ca5eabed40b1354c489b29 (diff)
Add the rt linux 4.1.3-rt3 as base
Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
Diffstat (limited to 'kernel/include/linux/blk-mq.h')
-rw-r--r--kernel/include/linux/blk-mq.h267
1 files changed, 267 insertions, 0 deletions
diff --git a/kernel/include/linux/blk-mq.h b/kernel/include/linux/blk-mq.h
new file mode 100644
index 000000000..e6ff990c9
--- /dev/null
+++ b/kernel/include/linux/blk-mq.h
@@ -0,0 +1,267 @@
+#ifndef BLK_MQ_H
+#define BLK_MQ_H
+
+#include <linux/blkdev.h>
+
+struct blk_mq_tags;
+struct blk_flush_queue;
+
+struct blk_mq_cpu_notifier {
+ struct list_head list;
+ void *data;
+ int (*notify)(void *data, unsigned long action, unsigned int cpu);
+};
+
+struct blk_mq_ctxmap {
+ unsigned int size;
+ unsigned int bits_per_word;
+ struct blk_align_bitmap *map;
+};
+
+struct blk_mq_hw_ctx {
+ struct {
+ spinlock_t lock;
+ struct list_head dispatch;
+ } ____cacheline_aligned_in_smp;
+
+ unsigned long state; /* BLK_MQ_S_* flags */
+ struct delayed_work run_work;
+ struct delayed_work delay_work;
+ cpumask_var_t cpumask;
+ int next_cpu;
+ int next_cpu_batch;
+
+ unsigned long flags; /* BLK_MQ_F_* flags */
+
+ struct request_queue *queue;
+ struct blk_flush_queue *fq;
+
+ void *driver_data;
+
+ struct blk_mq_ctxmap ctx_map;
+
+ unsigned int nr_ctx;
+ struct blk_mq_ctx **ctxs;
+
+ atomic_t wait_index;
+
+ struct blk_mq_tags *tags;
+
+ unsigned long queued;
+ unsigned long run;
+#define BLK_MQ_MAX_DISPATCH_ORDER 10
+ unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
+
+ unsigned int numa_node;
+ unsigned int queue_num;
+
+ atomic_t nr_active;
+
+ struct blk_mq_cpu_notifier cpu_notifier;
+ struct kobject kobj;
+};
+
+struct blk_mq_tag_set {
+ struct blk_mq_ops *ops;
+ unsigned int nr_hw_queues;
+ unsigned int queue_depth; /* max hw supported */
+ unsigned int reserved_tags;
+ unsigned int cmd_size; /* per-request extra data */
+ int numa_node;
+ unsigned int timeout;
+ unsigned int flags; /* BLK_MQ_F_* */
+ void *driver_data;
+
+ struct blk_mq_tags **tags;
+
+ struct mutex tag_list_lock;
+ struct list_head tag_list;
+};
+
+struct blk_mq_queue_data {
+ struct request *rq;
+ struct list_head *list;
+ bool last;
+};
+
+typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *);
+typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
+typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
+typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
+typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
+typedef int (init_request_fn)(void *, struct request *, unsigned int,
+ unsigned int, unsigned int);
+typedef void (exit_request_fn)(void *, struct request *, unsigned int,
+ unsigned int);
+
+typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
+ bool);
+
+struct blk_mq_ops {
+ /*
+ * Queue request
+ */
+ queue_rq_fn *queue_rq;
+
+ /*
+ * Map to specific hardware queue
+ */
+ map_queue_fn *map_queue;
+
+ /*
+ * Called on request timeout
+ */
+ timeout_fn *timeout;
+
+ softirq_done_fn *complete;
+
+ /*
+ * Called when the block layer side of a hardware queue has been
+ * set up, allowing the driver to allocate/init matching structures.
+ * Ditto for exit/teardown.
+ */
+ init_hctx_fn *init_hctx;
+ exit_hctx_fn *exit_hctx;
+
+ /*
+ * Called for every command allocated by the block layer to allow
+ * the driver to set up driver specific data.
+ *
+ * Tag greater than or equal to queue_depth is for setting up
+ * flush request.
+ *
+ * Ditto for exit/teardown.
+ */
+ init_request_fn *init_request;
+ exit_request_fn *exit_request;
+};
+
+enum {
+ BLK_MQ_RQ_QUEUE_OK = 0, /* queued fine */
+ BLK_MQ_RQ_QUEUE_BUSY = 1, /* requeue IO for later */
+ BLK_MQ_RQ_QUEUE_ERROR = 2, /* end IO with error */
+
+ BLK_MQ_F_SHOULD_MERGE = 1 << 0,
+ BLK_MQ_F_TAG_SHARED = 1 << 1,
+ BLK_MQ_F_SG_MERGE = 1 << 2,
+ BLK_MQ_F_SYSFS_UP = 1 << 3,
+ BLK_MQ_F_DEFER_ISSUE = 1 << 4,
+ BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
+ BLK_MQ_F_ALLOC_POLICY_BITS = 1,
+
+ BLK_MQ_S_STOPPED = 0,
+ BLK_MQ_S_TAG_ACTIVE = 1,
+
+ BLK_MQ_MAX_DEPTH = 10240,
+
+ BLK_MQ_CPU_WORK_BATCH = 8,
+};
+#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \
+ ((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \
+ ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1))
+#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \
+ ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
+ << BLK_MQ_F_ALLOC_POLICY_START_BIT)
+
+struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
+ struct request_queue *q);
+void blk_mq_finish_init(struct request_queue *q);
+int blk_mq_register_disk(struct gendisk *);
+void blk_mq_unregister_disk(struct gendisk *);
+
+int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set);
+void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
+
+void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
+
+void blk_mq_insert_request(struct request *, bool, bool, bool);
+void blk_mq_free_request(struct request *rq);
+void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq);
+bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
+ gfp_t gfp, bool reserved);
+struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
+
+enum {
+ BLK_MQ_UNIQUE_TAG_BITS = 16,
+ BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1,
+};
+
+u32 blk_mq_unique_tag(struct request *rq);
+
+static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag)
+{
+ return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS;
+}
+
+static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
+{
+ return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
+}
+
+struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
+struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
+void __blk_mq_complete_request_remote_work(struct work_struct *work);
+
+int blk_mq_request_started(struct request *rq);
+void blk_mq_start_request(struct request *rq);
+void blk_mq_end_request(struct request *rq, int error);
+void __blk_mq_end_request(struct request *rq, int error);
+
+void blk_mq_requeue_request(struct request *rq);
+void blk_mq_add_to_requeue_list(struct request *rq, bool at_head);
+void blk_mq_cancel_requeue_work(struct request_queue *q);
+void blk_mq_kick_requeue_list(struct request_queue *q);
+void blk_mq_abort_requeue_list(struct request_queue *q);
+void blk_mq_complete_request(struct request *rq);
+
+void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
+void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
+void blk_mq_stop_hw_queues(struct request_queue *q);
+void blk_mq_start_hw_queues(struct request_queue *q);
+void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
+void blk_mq_run_hw_queues(struct request_queue *q, bool async);
+void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
+void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
+ void *priv);
+void blk_mq_freeze_queue(struct request_queue *q);
+void blk_mq_unfreeze_queue(struct request_queue *q);
+void blk_mq_freeze_queue_start(struct request_queue *q);
+
+/*
+ * Driver command data is immediately after the request. So subtract request
+ * size to get back to the original request, add request size to get the PDU.
+ */
+static inline struct request *blk_mq_rq_from_pdu(void *pdu)
+{
+ return pdu - sizeof(struct request);
+}
+static inline void *blk_mq_rq_to_pdu(struct request *rq)
+{
+ return rq + 1;
+}
+
+#define queue_for_each_hw_ctx(q, hctx, i) \
+ for ((i) = 0; (i) < (q)->nr_hw_queues && \
+ ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++)
+
+#define queue_for_each_ctx(q, ctx, i) \
+ for ((i) = 0; (i) < (q)->nr_queues && \
+ ({ ctx = per_cpu_ptr((q)->queue_ctx, (i)); 1; }); (i)++)
+
+#define hctx_for_each_ctx(hctx, ctx, i) \
+ for ((i) = 0; (i) < (hctx)->nr_ctx && \
+ ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
+
+#define blk_ctx_sum(q, sum) \
+({ \
+ struct blk_mq_ctx *__x; \
+ unsigned int __ret = 0, __i; \
+ \
+ queue_for_each_ctx((q), __x, __i) \
+ __ret += sum; \
+ __ret; \
+})
+
+#endif